CN111178166A - Camera source identification method based on image content self-adaption - Google Patents
Camera source identification method based on image content self-adaption Download PDFInfo
- Publication number
- CN111178166A CN111178166A CN201911273277.0A CN201911273277A CN111178166A CN 111178166 A CN111178166 A CN 111178166A CN 201911273277 A CN201911273277 A CN 201911273277A CN 111178166 A CN111178166 A CN 111178166A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- noise
- subclass
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001914 filtration Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims 4
- 238000012935 Averaging Methods 0.000 claims 1
- 238000009826 distribution Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 229920006395 saturated elastomer Polymers 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a camera source identification method based on image content self-adaption. The method comprises the following steps: establishing a camera reference mode noise library, wherein each camera corresponds to a plurality of subclass reference mode noises, and different subclass reference mode noises reflect different image qualities and contents; judging the subclass of the image to be detected according to the quality and the content of the image, and calculating the noise residual of the image to be detected; and calculating the correlation between the noise residual of the image to be detected and the corresponding subclass reference mode noise of each camera in the camera reference mode noise library, and further determining the camera source of the image to be detected. The method can effectively reduce the identification error of the camera source.
Description
Technical Field
The invention relates to the technical field of camera source identification, in particular to a camera source identification method based on image content self-adaption.
Background
With the rapid update of modern digital products, digital images are becoming increasingly widely used in daily life. The development and application of digital image editing software make digital images easier to process, even counterfeit, maliciously tampered and the like. For example, when an image with copyright protection is re-photographed and released without authorization of a copyright owner, camera source identification technology can be used for forensics to distinguish whether a propagated image is an original image or an image copied by other cameras, so as to judge the copyright of the image. And if a certain part in one image is replaced by a certain part in a picture taken by another camera through image processing software, the scene in the image is changed, and the fact is changed, so that the camera source identification technology has important significance in cases of forensic evidence, academic counterfeiting, insurance claim and the like.
The camera typically generates an original image from the acquisition of a natural scene to the output of a digital image through several components including lenses, filters, color filter matrix, and sensors, where sensor pattern noise is an important and stable camera fingerprint. According to the sensor pattern noise, not only can the brand of the camera be distinguished, but also different models of the same brand of camera can be distinguished. The sensor mode noise is mainly caused by two reasons, namely inevitable flaws in the sensor production process and the photosensitive difference of each pixel caused by the nonuniformity of a silicon wafer. Even sensors made from the same silicon wafer will have uncorrelated pattern noise due to imperfections in the sensor manufacturing process and the variable light sensing characteristics of each pixel. Sensor pattern noise is a robust camera fingerprint.
The existing camera source identification technology mainly obtains the reference mode noise of each camera by filtering the original images of all known camera sources in a database; and for the test image, filtering by using the same filter to obtain a noise residual, then calculating a correlation coefficient between the noise of the camera reference mode and the noise residual of the image to be detected, determining a camera source of the image to be detected according to the magnitude of the correlation coefficient, and not considering the influence of images with different qualities in an image database on camera source identification.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a camera source identification method based on image content self-adaptation, which considers the influence of image content and quality in an image database on camera source identification and can effectively reduce camera source identification errors.
The invention provides a camera source identification method based on image content self-adaption. The method comprises the following steps:
establishing a camera reference mode noise library, wherein each camera corresponds to a plurality of subclass reference mode noises, and different subclass reference mode noises reflect different image qualities and contents;
judging the subclass of the image to be detected according to the quality and the content of the image, and calculating the noise residual of the image to be detected;
and calculating the correlation between the noise residual of the image to be detected and the corresponding subclass reference mode noise of each camera in the camera reference mode noise library, and further determining the camera source of the image to be detected.
In one embodiment, the establishing a camera reference pattern noise library comprises:
calculating the mean and variance of each image for a library of images of known camera sources and of different quality;
dividing the image library into a plurality of subclasses according to the size of the mean value and the variance;
and filtering the images in the plurality of sub-classes, and respectively calculating the reference mode noise of all the images shot by the same camera in the plurality of sub-classes.
In one embodiment, the reference pattern noise for each sub-class is averaged over the noise residuals of all the images of the camera in that sub-class.
In one embodiment, for an image, its corresponding sub-class is determined from the mean and variance of the image, and is expressed as:
wherein ,AijDenotes the pixel value at point (i, j) of image A, m denotes the image mean, v denotes the image variance, C1、C2、C3Is a subclass identification.
In one embodiment, the reference pattern noise for each subclass of camera sources is calculated according to the following formula:
Nij＝Aij-Aij*F
wherein, denotes a convolution operation, AijRepresents the pixel value at point (i, j) of image a, F is the filter template, expressed as:
in one embodiment, for the image P under test, the noise residual N is calculated by the following formulaPCorrelation coefficient between subclass reference pattern noise corresponding to each camera:
wherein ,
representing the mean value, R, of all elements in the noise residual image of the image to be measuredMRepresenting the subclass of reference pattern noise of the camera M,
represents the mean value of each subclass of reference pattern noise of the camera M.
Compared with the prior art, the invention has the advantages that: in the prior art, image libraries of known camera sources are filtered uniformly to obtain reference pattern noise of the camera sources, and the influence of various images with different contents and qualities in the image libraries on the extraction of the reference pattern noise of the camera sources is not considered; in the camera source identification process, the prior art only uses the noise residual of the image to be detected and the camera source reference mode noise to carry out correlation calculation, but the invention firstly judges the subclass of the image to be detected and then carries out correlation calculation with the corresponding subclass reference mode noise, and the image quality and content are utilized, so that the camera source identification error can be effectively reduced.
Drawings
The invention is illustrated and described only by way of example and not by way of limitation in the scope of the invention as set forth in the following drawings, in which:
fig. 1 is a flowchart of a camera source recognition method based on image content adaptation according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions, design methods, and advantages of the present invention more apparent, the present invention will be further described in detail by specific embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
Under the premise that a large number of image libraries with known camera sources and different qualities exist, the camera source identification method mainly comprises the following steps: firstly, dividing pictures shot by each camera into a plurality of subclasses according to the quality and the content of the images; then, filtering each subclass, and respectively calculating the reference mode noise of each camera under a plurality of subclasses; for a given image to be detected, judging which subclass the given image to be detected belongs to, and then filtering the image to be detected to obtain a noise residual error of the image to be detected; and finally, calculating a correlation coefficient between the noise residual of the image to be detected and the noise of the camera reference mode of the corresponding subclass, and further judging the camera source of the image to be detected.
Specifically, referring to fig. 1, the camera source identification method according to the embodiment of the present invention includes:
in step S110, the images captured by the respective camera sources are divided into a plurality of sub-categories based on image quality and content.
In one embodiment, the images are sub-classified according to:
first, the mean and variance of each image are calculated from a library C of a large number of images of known camera sources and of different quality.
Suppose an image A ∈ RH×WWhere H and W represent the height and width, respectively, of image a, then the mean m and variance v, respectively, can be calculated using the following equations:
wherein ,AijRepresenting the pixel value at point (i, j) of image a.
The image library is then divided into subsets (or subclasses) according to the size of the mean and variance.
For example, the image library is divided into three subsets, represented as saturation, smoothing, and other three categories. The larger the variance is, the more dispersed the pixel point distribution of the image is; conversely, the smaller the variance, the more concentrated the distribution of the pixels of the image. In one embodiment, it is set that when the variance v ≦ 20, the mean 0 ≦ m ≦ 5 or 250 ≦ m ≦ 255, the image is considered to belong to the saturation category; when the variance is more than 20 and less than or equal to 50, the mean value is more than or equal to 0 and less than or equal to 5 or more than or equal to 250 and m is more than or equal to 255, the variance is more than or equal to 0 and less than or equal to 50, and the mean value is more than 5 and less than or equal to m and less than 250, the image is considered to belong to the; the rest are divided into other categories. Specifically, it can be represented by the following formula (3):
wherein C1Is a collection of saturated images, C2Is a collection of smoothed images, C3Is a collection of other classes.
In the above manner, C is obtained for all image groups captured by the same type of camera MM＝{CM1,CM2,CM3}, wherein CM1、CM2 and CM3Respectively saturated, smoothed and other three subsets of the pictures taken by the camera M.
It is to be noted that, those skilled in the art can make appropriate changes or modifications to the embodiments herein based on the spirit and principles of the present invention, for example, the image can be divided into more subsets according to the size of the mean and variance, and is not limited to only three subsets, and in practical applications, the number of the divided subsets can be determined according to the content of the captured image, the gradual improvement of the camera resolution technology, and the like. For clarity, three subsets are described below.
Step S120, filtering the images of the subclasses to obtain reference pattern noise corresponding to each subclass, and further establishing a camera reference pattern noise library.
Specifically, the images in the three subsets are respectively subjected to high-pass denoising and filtering, and the filter template may adopt a high-pass filter, which is expressed as:
the high-pass denoising filter can suppress interference brought by image edges and textures to camera source reference noise.
The camera source reference pattern noise may be expressed as:
Nij＝Aij-Aij*F (5)
where denotes the convolution operation.
All image groups C shot by the same camera MM＝{CM1,CM2,CM3Calculating the reference pattern noise in three subsetsAnd (4) sound. For example, the reference pattern noise for each subset is averaged over the noise residuals of all pictures of the camera in that subset. Finally, for each camera M, three reference pattern noises are obtained, namely the reference pattern noise R of the saturated subsetM1Smoothing of the reference pattern noise R of the subsetM2And reference pattern noise R of other subsetsM3And then build a fingerprint library of the camera (i.e., a camera reference pattern noise library).
Step S130, for the image to be detected, camera source identification is carried out based on the image quality and content and the established camera reference pattern noise library.
Specifically, a to-be-detected image P is given, the mean value and the variance of the to-be-detected image P are calculated firstly, and the subclass to which the to-be-detected image P belongs is judged according to the formula (3); then, the image is filtered by a high-pass filter represented by formula (4), and a noise residual N of the image to be measured is calculated by formula (6)P。
NP＝P-P*F (6)
Finally, the noise residual N is calculatedPSub-class reference pattern noise (R) corresponding to each cameraM1Or RM2Or RM3) The correlation coefficient between them is expressed as:
wherein ,
representing the mean value, R, of all elements in the noise residual image of the image to be measuredMRepresenting the reference pattern noise of camera M, which may be RM1，RM2Or RM3Any one of them is determined by which subclass the picture P to be measured belongs to. For example, when P belongs to the saturated subclass, RMGet RM1(ii) a When P belongs to the smoothing subclass, RMGet RM2(ii) a When P belongs to other subclasses, RMGet RM3。
Representing each subclass of reference pattern noise of camera MMean value of the sounds.
Further, a parametric model may be built to determine the distribution of noise residual correlations across all images captured by the camera source. To minimize the false rejection rate of the camera source while imposing a constraint on the false acceptance rate, a threshold can be experimentally designed using the Neyman-Pearson criterion (probabilit-false alarm probability) to determine the ρ of an image Q from the camera source MM(Q) and the image Q' is not from ρ of the camera source MM(Q') distribution range. Comparison of the correlations ρM(P) and the threshold value, thereby determining whether the image P to be predicted is derived from the camera M.
It should be understood that, for the calculation formula (7) of the correlation coefficient, other evaluation indexes such as peak-to-correlation energy (PCE) or circular cross-correlation norm (CCN) may be used instead in practice, and the object of the present invention may also be achieved.
To verify the effect of the invention, it is possible to base the premise on a large number of known camera sources and different quality Image libraries, for example the classic Database of camera source identification the Dresden Image Database, which provides over 16000 pictures of different quality taken from 74 camera devices. The image is divided into three subclasses according to the distribution of the mean and variance according to equations (1), (2) and (3), and then the reference pattern noise of each camera source of each subclass is found. And finally, calculating the mean value and the variance distribution of the image P to be detected to obtain the category of the image P to be detected, and filtering by using a high-pass filter represented by a formula (4) to obtain the noise residual of the image to be detected. And obtaining the camera source of the image to be detected by calculating the correlation coefficient between the noise residual of the image to be detected and the reference mode noise of the camera source in the corresponding category. These mean and variance calculations, as well as camera source reference pattern noise, noise residuals of the image, etc. can all be implemented by MATLAB functions.
Through verification, compared with a saturated image containing limited information, the method can obtain more reliable reference pattern noise from a smooth and bright image, and can more accurately identify the camera source of the image to be detected through a camera fingerprint library which is established based on the quality and the content of the image and contains a plurality of subclasses of reference pattern noise.
It should be noted that, although the steps are described in a specific order, the steps are not necessarily performed in the specific order, and in fact, some of the steps may be performed concurrently or even in a changed order as long as the required functions are achieved.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that retains and stores instructions for use by an instruction execution device. The computer readable storage medium may include, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (8)
1. A camera source identification method based on image content self-adaptation comprises the following steps:
establishing a camera reference mode noise library, wherein each camera corresponds to a plurality of subclass reference mode noises, and different subclass reference mode noises reflect different image qualities and contents;
judging the subclass of the image to be detected according to the quality and the content of the image, and calculating the noise residual of the image to be detected;
and calculating the correlation between the noise residual of the image to be detected and the corresponding subclass reference mode noise of each camera in the camera reference mode noise library, and further determining the camera source of the image to be detected.
2. The image content adaptive-based camera source recognition method of claim 1, wherein the establishing a camera reference pattern noise library comprises:
calculating the mean and variance of each image for a library of images of known camera sources and of different quality;
dividing the image library into a plurality of subclasses according to the size of the mean value and the variance;
and filtering the images in the plurality of sub-classes, and respectively calculating the reference mode noise of all the images shot by the same camera in the plurality of sub-classes.
3. The method of claim 2, wherein the reference pattern noise of each sub-class is determined by averaging the noise residuals of all images of the camera in the sub-class.
4. The image content adaptive-based camera source identification method according to claim 1, wherein for one image, the corresponding sub-class is determined according to the mean and variance of the image, and is represented as:
wherein ,AijDenotes the pixel value at point (i, j) of image A, m denotes the image mean, v denotes the image variance, C1、C2、C3Is a subclass identification.
5. The image content adaptive camera source recognition-based method according to claim 1, wherein the reference pattern noise of each subclass of camera sources is calculated according to the following formula:
Nij＝Aij-Aij*F
wherein, denotes a convolution operation, AijRepresents the pixel value at point (i, j) of image a, F is the filter template, expressed as:
6. the image content adaptive-based camera source identification method according to claim 1, wherein for the image P to be detected, the noise residual N is calculated by the following formulaPCorrelation coefficient between subclass reference pattern noise corresponding to each camera:
wherein ,
representing the mean value, R, of all elements in the noise residual image of the image to be measuredMRepresenting the subclass of reference pattern noise of the camera M,
represents the mean value of each subclass of reference pattern noise of the camera M.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
8. A computer device comprising a memory and a processor, on which memory a computer program is stored which is executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911273277.0A CN111178166B (en) | 2019-12-12 | 2019-12-12 | Camera source identification method based on image content self-adaption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911273277.0A CN111178166B (en) | 2019-12-12 | 2019-12-12 | Camera source identification method based on image content self-adaption |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111178166A true CN111178166A (en) | 2020-05-19 |
| CN111178166B CN111178166B (en) | 2023-05-26 |
Family
ID=70646340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911273277.0A Active CN111178166B (en) | 2019-12-12 | 2019-12-12 | Camera source identification method based on image content self-adaption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178166B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951254A (en) * | 2020-08-18 | 2020-11-17 | 济南大学 | Source camera identification method and system based on edge-guided weighted average |
| CN115102735A (en) * | 2022-06-15 | 2022-09-23 | 蚂蚁区块链科技(上海)有限公司 | Image authentication method and device |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020118887A1 (en) * | 2000-12-20 | 2002-08-29 | Eastman Kodak Company | Multiresolution based method for removing noise from digital images |
| US20030179944A1 (en) * | 2002-03-20 | 2003-09-25 | Eastman Kodak Company | Calculating noise from multiple digital images having a common noise source |
| US20080158426A1 (en) * | 2006-12-27 | 2008-07-03 | Yi-Jen Chiu | Method and apparatus for content adaptive spatial-temporal motion adaptive noise reduction |
| CN102819831A (en) * | 2012-08-16 | 2012-12-12 | 江南大学 | Camera source evidence obtaining method based on mode noise big component |
| CN103593645A (en) * | 2013-10-11 | 2014-02-19 | 合肥工业大学 | Method for identifying source camera of cutout image |
| CN106056639A (en) * | 2016-05-24 | 2016-10-26 | 大连理工大学 | Steganography method based on camera source anti-forensics |
| US9525866B1 (en) * | 2016-04-18 | 2016-12-20 | The United States Of America As Represented By The Director, National Security Agency | Building a digital camera fingerprint from cropped or corrupted images |
| CN106408036A (en) * | 2015-07-30 | 2017-02-15 | 中国科学院深圳先进技术研究院 | Method and system for image camera source identification |
| CN106851140A (en) * | 2016-12-05 | 2017-06-13 | 宁波大学 | A kind of digital photo images source title method of use spatial domain smothing filtering |
| CN110188828A (en) * | 2019-05-31 | 2019-08-30 | 大连理工大学 | A kind of image sources discrimination method based on virtual sample integrated study |
| CN110210498A (en) * | 2019-05-31 | 2019-09-06 | 北京交通大学 | Digital image device evidence-obtaining system based on residual error study convolution converged network |
| US10460212B1 (en) * | 2017-10-24 | 2019-10-29 | U.S. Government As Represented By The Director, National Security Agency | Binning digital images by source camera |
-
2019
- 2019-12-12 CN CN201911273277.0A patent/CN111178166B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020118887A1 (en) * | 2000-12-20 | 2002-08-29 | Eastman Kodak Company | Multiresolution based method for removing noise from digital images |
| US20030179944A1 (en) * | 2002-03-20 | 2003-09-25 | Eastman Kodak Company | Calculating noise from multiple digital images having a common noise source |
| US20080158426A1 (en) * | 2006-12-27 | 2008-07-03 | Yi-Jen Chiu | Method and apparatus for content adaptive spatial-temporal motion adaptive noise reduction |
| CN102819831A (en) * | 2012-08-16 | 2012-12-12 | 江南大学 | Camera source evidence obtaining method based on mode noise big component |
| CN103593645A (en) * | 2013-10-11 | 2014-02-19 | 合肥工业大学 | Method for identifying source camera of cutout image |
| CN106408036A (en) * | 2015-07-30 | 2017-02-15 | 中国科学院深圳先进技术研究院 | Method and system for image camera source identification |
| US9525866B1 (en) * | 2016-04-18 | 2016-12-20 | The United States Of America As Represented By The Director, National Security Agency | Building a digital camera fingerprint from cropped or corrupted images |
| CN106056639A (en) * | 2016-05-24 | 2016-10-26 | 大连理工大学 | Steganography method based on camera source anti-forensics |
| CN106851140A (en) * | 2016-12-05 | 2017-06-13 | 宁波大学 | A kind of digital photo images source title method of use spatial domain smothing filtering |
| US10460212B1 (en) * | 2017-10-24 | 2019-10-29 | U.S. Government As Represented By The Director, National Security Agency | Binning digital images by source camera |
| CN110188828A (en) * | 2019-05-31 | 2019-08-30 | 大连理工大学 | A kind of image sources discrimination method based on virtual sample integrated study |
| CN110210498A (en) * | 2019-05-31 | 2019-09-06 | 北京交通大学 | Digital image device evidence-obtaining system based on residual error study convolution converged network |
Non-Patent Citations (2)
| Title |
|---|
| ABBAS EBRAHIMI-MOGHADAM 等: "Sub-Optimal MMSE Based Joint Source/Channel Decoding of a Matching Pursuit Coded Image Bit-Stream Over a Memoryless Noisy Channel", 《2008 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO》 * |
| YUAN-GEN WANG 等: "An improved sample projection approach for image watermarking", 《DIGITAL SIGNAL PROCESSING》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951254A (en) * | 2020-08-18 | 2020-11-17 | 济南大学 | Source camera identification method and system based on edge-guided weighted average |
| CN111951254B (en) * | 2020-08-18 | 2024-05-10 | 济南大学 | Edge-guided weighted-average-based source camera identification method and system |
| CN115102735A (en) * | 2022-06-15 | 2022-09-23 | 蚂蚁区块链科技(上海)有限公司 | Image authentication method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111178166B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pun et al. | Multi-scale noise estimation for image splicing forgery detection | |
| Chierchia et al. | On the influence of denoising in PRNU based forgery detection | |
| Liu et al. | A passive image authentication scheme for detecting region-duplication forgery with rotation | |
| Yao et al. | Detecting image splicing based on noise level inconsistency | |
| Piva | An overview on image forensics | |
| CN108875731B (en) | Target identification method, device, system and storage medium | |
| CN109376631B (en) | Loop detection method and device based on neural network | |
| Chierchia et al. | PRNU-based detection of small-size image forgeries | |
| Qiao et al. | Individual camera device identification from JPEG images | |
| US20130223751A1 (en) | Method, apparatus and computer program product for providing pattern detection with unknown noise levels | |
| CN111178166B (en) | Camera source identification method based on image content self-adaption | |
| CN111079816A (en) | Image auditing method and device and server | |
| CN111368944B (en) | Method and device for recognizing copied image and certificate photo and training model and electronic equipment | |
| JP2012058787A (en) | Information processor and processing method thereof | |
| CN110909712A (en) | Moving object detection method and device, electronic equipment and storage medium | |
| Muhammad et al. | A non-intrusive method for copy-move forgery detection | |
| CN112395118A (en) | Equipment data detection method and device | |
| CN111031359B (en) | Video playing method and device, electronic equipment and computer readable storage medium | |
| JP2017511674A (en) | System for identifying a photo camera model associated with a JPEG compressed image, and associated methods, uses and applications | |
| Cozzolino et al. | Multimedia forensics before the deep learning era | |
| CN117392464B (en) | Image anomaly detection method and system based on multi-scale denoising probability model | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN111178200A (en) | Identification method of instrument panel indicator lamp and computing equipment | |
| Julliand et al. | Automatic image splicing detection based on noise density analysis in raw images | |
| Zeng et al. | Exposing image splicing with inconsistent sensor noise levels |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |